GitHub
Start free
Dashboard
Start freeSign inDashboard

Nemotron 3.5 Super VL

by NVIDIA · nvidia/nemotron-3.5-super-vl

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

Use in KryptonUse in Krypton
Input / 1M tokens
$0.15
Output / 1M tokens
$0.50
Context
1.05M

Specs

Input price$0.15 / 1M tokens
Output price$0.50 / 1M tokens
Cached input$0.02 / 1M tokens
Context window1.05M tokens
Max output236K tokens
Readstext, image, video
Writestext
Tool callingYes
ReasoningYes
ListedOct 15, 2026

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

9 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderQuantizationContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
DarkbloomCheapestnvfp4262K32.8K$0.06$0.35$0.01—1.90 s42 tok/sNormal
Crusoebf161.05M262K$0.10$0.40$0.08100%297 ms170 tok/sNormal
CoreWeavenvfp41.05M944K$0.15$0.50$0.02100%407 ms334 tok/sCode -2
DeepInfraFastestfp4262K236K$0.15$0.50$0.02100%434 ms578 tok/sNormal
Io Netnvfp4262K131K$0.15$0.50$0.02100%1.19 s66 tok/sNormal
Together—262K236K$0.15$0.50$0.02100%557 ms115 tok/sNormal
BaseTenfp41.05M944K$0.20$0.50$0.04100%1.36 s178 tok/sNormal
Venicefp4262K32.8K$0.20$0.50$0.0480%423 ms352 tok/sCode -2
Nebiusbf161.05M944K$0.30$0.90$0.06100%1.82 s116 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.

All models